Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讶
    -0.07
     sous
    -0.07
    =S
    -0.07
    级
    -0.07
     survival
    -0.07
    北宋
    -0.07
     radicals
    -0.07
     objeto
    -0.07
    יכות
    -0.07
     ترك
    -0.07
    POSITIVE LOGITS
    ILTER
    0.07
    igators
    0.07
    اوي
    0.07
    뎬
    0.07
    文学
    0.06
    _case
    0.06
    ']]['
    0.06
    "}}↵
    0.06
    克制
    0.06
     naw
    0.06
    Act Density 0.000%

    No Known Activations